Source Data-Absent Unsupervised Domain Adaptation Through Hypothesis Transfer and Labeling Transfer
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a related but different well-labeled source domain to a new unlabeled target domain. Most existing UDA methods require access to the source data, and thus are not applicable when the data are confidential and not shareable due to p...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 11 vom: 24. Nov., Seite 8602-8617
|
|---|
| 1. Verfasser: |
Liang, Jian
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Hu, Dapeng,
Wang, Yunbo,
He, Ran,
Feng, Jiashi |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2022
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|